Year: 2022
Type: preprint
Abstract: High-quality data plays a central role in ensuring the accuracy of policy evaluation. This paper initiates the study of efficient and safe data collection for bandit policy evaluation. We formulate the problem and investigate its several representative variants. For each variant, we analyze its statistical properties, derive the corresponding exploration policy, and design an efficient algorithm for computing it. Both theoretical analysis and experiments support the usefulness of the proposed methods.
Source: arXiv (Cornell University)
Authors: Wan, Runzhe, Kveton, Branislav, Song, Rui
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W4221161267